Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Python errors/tracebacks

    np_max-act · gemini-2.0-flash

    The neuron activates on Python stack‐trace lines (traceback entries with file paths, line numbers, and code context).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     semiclass
    -0.07
    .numberOf
    -0.07
    、《
    -0.06
     tả
    -0.06
    타이
    -0.06
    	spin
    -0.06
     �
    -0.06
     토
    -0.06
    .Line
    -0.06
    .pop
    -0.06
    POSITIVE LOGITS
     luck
    0.07
     digital
    0.06
     problem
    0.06
     disabilities
    0.06
    езд
    0.06
     scams
    0.06
    输出
    0.06
     nouvelles
    0.06
     predicting
    0.06
     Δια
    0.06
    Act Density 0.003%

    No Known Activations